Time Series Forecasting
Diffusers
Safetensors
time-series
diffusion
scenario-generation
weather
multivariate-time-series
Eval Results (legacy)
Instructions to use kyLELEng/weather-scenario-diffusion-1d with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kyLELEng/weather-scenario-diffusion-1d with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("kyLELEng/weather-scenario-diffusion-1d", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Add explicit parameter count
Browse files
README.md
CHANGED
|
@@ -28,6 +28,13 @@ The model uses:
|
|
| 28 |
- `diffusers.DDPMScheduler`
|
| 29 |
- mask conditioning through concatenated input channels: `noisy_x`, `observed_x`, and `observed_mask`
|
| 30 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
## Data
|
| 32 |
|
| 33 |
- Source dataset: `Duyu/Time-Series-Forecasting-Benchmark-Datasets`
|
|
|
|
| 28 |
- `diffusers.DDPMScheduler`
|
| 29 |
- mask conditioning through concatenated input channels: `noisy_x`, `observed_x`, and `observed_mask`
|
| 30 |
|
| 31 |
+
## Model Size
|
| 32 |
+
|
| 33 |
+
- Parameters: `41,556,501`
|
| 34 |
+
- Weight dtype: `float32`
|
| 35 |
+
- Weight file: `diffusion_pytorch_model.safetensors`
|
| 36 |
+
- Weight file size: approximately `166 MB`
|
| 37 |
+
|
| 38 |
## Data
|
| 39 |
|
| 40 |
- Source dataset: `Duyu/Time-Series-Forecasting-Benchmark-Datasets`
|